delegate

delegate is a command for coding agents from xzawed/claude-grok-build-plugin. It costs 7 tokens per session (362 once invoked), scanned A, original, MIT.

A command for sending a coding task to Grok Build after checking that it is ready and that delegation is suitable.

In plain words
What is it for?
Use it to delegate approved coding tasks, isolate broad changes in a worktree, and continue a later task with its session ID.
Why use it?
It avoids sending unsuitable or risky work to the coding worker and makes the result, changed files, and configured billing mode visible for review.

Command

Part of the grok plugin — 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/xzawed/claude-grok-build-plugin/delegate
Clone the repo
git clone --depth 1 https://github.com/xzawed/claude-grok-build-plugin

Or install grok, the plugin that ships this one along with the rest of its 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for delegate

README.md
[![agentmods](https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/delegate.svg)](https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/delegate)
Your own site
<a href="https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/delegate"><img src="https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/delegate.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.00362
Opus 5 $0.00003 $0.00181
Sonnet 5 $0.00001 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 4d ago against content hash bd72d2d4f03c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

delegate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/delegate.md · 28 lines

What it actually says

Call grok_build_status first (or grok_auth_check when you only need auth). If ready is false, stop and show the message. If it reports billingMismatch, tell the user that the server is in subscription mode but their delegation history contains metered runs, so GROK_BUILD_AUTH_MODE was api for some of them. The flag is about past history, not a prediction that the next call will bill as metered.

If the task's fit for Grok is unclear, call grok_build_route and follow nextAction. When it says handle_with_claude, do not force Grok. When nextAction.requiresHumanGateBeforeDelegate is set, run grok_build_plan and wait for the user's approval before any edit.

Otherwise call grok_build_delegate with the user's task as prompt and an absolute cwd. For wide or risky edits pass worktree: true, so changes land in an isolated worktree instead of the working tree.

Show the returned summary, filesChanged, and — importantly — the billing field, so the user sees which mode the server was configured in. It is a tag derived from GROK_BUILD_AUTH_MODE, not a measured charge. If the result includes sessionId, note that a follow-up can use /grok:resume (or resume on the next delegate).

Finish at the review gate: run /grok:review on the diff. Do not commit — the user decides accept, fix, or discard.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 28 lines · 7 tokens per session scan A bd72d2d4f03c

Subscribe to this mod's changes

delegate is a command published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 362 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.